End of training

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 3.0,
     "eval_accuracy": 0.2857142857142857,
     "eval_loss": 0.7827825546264648,
-    "eval_runtime": 0.7631,
-    "eval_samples_per_second": 9.173,
-    "eval_steps_per_second": 1.31,
+    "eval_runtime": 0.7719,
+    "eval_samples_per_second": 9.069,
+    "eval_steps_per_second": 1.296,
     "total_flos": 4250374116581376.0,
     "train_loss": 0.17864632606506348,
-    "train_runtime": 50.2769,
-    "train_samples_per_second": 3.401,
-    "train_steps_per_second": 0.06
+    "train_runtime": 45.1081,
+    "train_samples_per_second": 3.791,
+    "train_steps_per_second": 0.067
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 3.0,
     "eval_accuracy": 0.2857142857142857,
     "eval_loss": 0.7827825546264648,
-    "eval_runtime": 0.7631,
-    "eval_samples_per_second": 9.173,
-    "eval_steps_per_second": 1.31
+    "eval_runtime": 0.7719,
+    "eval_samples_per_second": 9.069,
+    "eval_steps_per_second": 1.296
 }

runs/May28_20-29-12_38183ecde2ad/events.out.tfevents.1653769965.38183ecde2ad.92.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0314f2fc5883fd130b79edb3239ac9872e4642746d66e561b0076e0b154a05ce
+size 357

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 3.0,
     "total_flos": 4250374116581376.0,
     "train_loss": 0.17864632606506348,
-    "train_runtime": 50.2769,
-    "train_samples_per_second": 3.401,
-    "train_steps_per_second": 0.06
+    "train_runtime": 45.1081,
+    "train_samples_per_second": 3.791,
+    "train_steps_per_second": 0.067
 }

trainer_state.json

@@ -11,27 +11,27 @@
       "epoch": 1.0,
       "eval_accuracy": 0.2857142857142857,
       "eval_loss": 0.7827825546264648,
-      "eval_runtime": 0.7129,
-      "eval_samples_per_second": 9.819,
-      "eval_steps_per_second": 1.403,
+      "eval_runtime": 0.7023,
+      "eval_samples_per_second": 9.967,
+      "eval_steps_per_second": 1.424,
       "step": 1
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.14285714285714285,
       "eval_loss": 0.8606036901473999,
-      "eval_runtime": 0.7151,
-      "eval_samples_per_second": 9.789,
-      "eval_steps_per_second": 1.398,
+      "eval_runtime": 0.6969,
+      "eval_samples_per_second": 10.044,
+      "eval_steps_per_second": 1.435,
       "step": 2
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.2857142857142857,
-      "eval_loss": 0.8618679046630859,
-      "eval_runtime": 0.7739,
-      "eval_samples_per_second": 9.045,
-      "eval_steps_per_second": 1.292,
+      "eval_loss": 0.8618678450584412,
+      "eval_runtime": 0.7824,
+      "eval_samples_per_second": 8.947,
+      "eval_steps_per_second": 1.278,
       "step": 3
     },
     {
@@ -39,9 +39,9 @@
       "step": 3,
       "total_flos": 4250374116581376.0,
       "train_loss": 0.17864632606506348,
-      "train_runtime": 50.2769,
-      "train_samples_per_second": 3.401,
-      "train_steps_per_second": 0.06
+      "train_runtime": 45.1081,
+      "train_samples_per_second": 3.791,
+      "train_steps_per_second": 0.067
     }
   ],
   "max_steps": 3,